ANALYTICAL HIERARCHY PROCESS, SIMPLE ADDITIVE WEIGHTING MENGGUNAKAN NAÏVE BAYES UNTUK DIAGNOSIS RISIKO PENYAKIT JANTUNG

Abstract

Every year, more than 36 million people die, one of which is due to cardiovascular disease, which means diseases caused by impaired function of the heart and blood vessels, such as coronary heart disease, heart failure or chronic heart disease, hypertension and stroke. The aim of this research is to develop a Decision Support System (DSS) that can be used to diagnose the level of risk of heart disease in patients using the Simple Additive Weighting (SAW), Analytic Hierarchy Process (AHP) method and using Naive Bayes classification to obtain experimental results showing accuracy is relatively high more than 85% and shows that the Naive Bayes model can make accurate predictions. The highest level of accuracy was found in the 80:20 data split ratio, which reached 87%. Data sharing ratios of 60:40 and 70:30, on the other hand, reach 86% and 85%, respectively. A low MAE indicates a small difference between the predicted value and the actual value in each trial; This shows the accuracy of the model in making predictions. Has a lower grade for first grade, or "Medium" grade. However, the precision, recall, and f1-score values in the "High" class (class 2) show that the model can easily distinguish patients with a high risk of heart disease.